skill-developer

Create and manage Claude Code skills with structured SKILL.md files and skill-rules.json.

9|4|Updated Jan 6, 2026
One-click install
npx skills add https://github.com/rafaelkamimura/claude-tools --skill skill-developer-rafaelkamimura
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-developer
Source: https://github.com/rafaelkamimura/claude-tools/tree/main/skills/skill-developer
Command: npx skills add https://github.com/rafaelkamimura/claude-tools --skill skill-developer-rafaelkamimura

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Centralized guidance and guardrails for creating and managing Claude Code skills.

Core Features & Use Cases

  • Two-hook architecture for proactive prompts and pre-tool safeguards, plus a structured skill-rules.json configuration to define triggers, priorities, and enforcement.
  • Progressive disclosure with reference documents and SKILL.md frontmatter to keep skills concise while offering deeper guidance when needed.
  • End-to-end workflow for creating, testing, and maintaining skills, including skip conditions, session tracking, and best-practice validation.

Quick Start

Define a new skill by placing .claude/skills/{name}/SKILL.md with frontmatter, add an entry to .claude/skills/skill-rules.json, and validate behavior using the provided hooks and test commands.

Frequently Asked Questions about skill-developer

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create and manage Claude Code skills with proper guardrails?

To create Claude Code skills, you define a SKILL.md file with valid YAML frontmatter, configure triggers and priorities in skill-rules.json, and implement a two-hook architecture for proactive prompts and pre-tool safeguards.

What is progressive disclosure in skill development and when should I use reference files?

Progressive disclosure is a technique that keeps skill definitions concise in SKILL.md while offering deeper domain guidance through separate reference files, triggered only when needed by specific hook mechanisms.

Why does my skill activation flow fail to trigger correctly?

Skill activation flows fail when the YAML frontmatter is invalid, the SKILL.md structure is malformed, or the trigger patterns and skip conditions defined in skill-rules.json do not match the expected hook mechanisms.

Can I use a two-hook architecture for proactive prompts and pre-tool safeguards?

Yes, a two-hook architecture allows you to implement proactive prompts for user guidance and pre-tool safeguards to enforce domain rules, ensuring robust validation before tool execution.

What's the best way to validate YAML frontmatter and trigger patterns for debugging skills?

The best way to validate skills is by using the provided hooks and test commands to enforce YAML frontmatter validity, verify SKILL.md structure, and debug trigger patterns and session tracking.

Do I need to update skill-rules.json manually when adding new domain skills?

Yes, you must manually add an entry to skill-rules.json to define triggers, priorities, and enforcement levels whenever you place a new .claude/skills/{name}/SKILL.md file for your domain skills.